Software Developer – Machine Learning

Santiago is a Software Developer specialising in machine learning, who has a passion for metagenomics and Mexican folk music.Santiago Sanchez Fragoso, Software Developer – Machine Learning at EMBL-EBI.Credit: Jeff Dowling/EMBL-EBI"We're incredibly fortunate to have access to this much data and it's vital for the work I do to train machine learning algorithms."Machine learning is embedded in different areas across EMBL's European Bioinformatics Institute (EMBL-EBI) including our data resources.Using this technology allows us to input data into our resources more efficiently than ever before.Santiago Sanchez Fragoso is a Software Developer at EMBL-EBI specialising in machine learning.Here, we find out about how he got into this field and his work to improve MGnify – our metagenomics data resource.What is your professional background?I did my Bachelor's degree in environmental biology and for my dissertation project, I developed a tool to identify proteins in arthropods – a type of insect – and plants.This was my first experience using pattern recognition and machine learning techniques.I then did a Master's degree which allowed me to develop these methods further.I did this in Cuernavaca, Mexico.This region is a hub for research, there are many life science institutes based there.What does your role entail?I'm a Software Developer specialising in machine learning.I develop tools and software for natural products discovery in the MGnify data resource.I also help with the development and rolling out of the new MGnify releases.Finally, I have my own research within the MGnify team.For this, I am testing the different tools I develop with various datasets to optimise them and gain new insights from these data.We also collaborate with colleagues at Cambridge University to help us validate our findings experimentally.What motivated you to work at EMBL-EBI?I was using EMBL-EBI resources and tools back in Mexico so working at the institute was an exciting opportunity.EMBL-EBI data resources are widely used in Mexico.For example, I was frequently using InterPro, Uniprot and Ontology Search to name a few.Metagenomics is also a very dynamic and fast growing area of bioinformatics so I saw this position in MGnify as a fantastic career opportunity.Working in bioinformatics meant I often took for granted the huge amount of data available in open access databases like those at EMBL-EBI.We're incredibly fortunate to have access to this much data and it's vital for the work I do to train machine learning algorithms.This has a huge impact on accelerating life science research.What are some of the challenges in your job?Working with big data always has its challenges; there's often a trade-off between how fast you want your work done versus the quality of the results.You find yourself frequently juggling this.There's an enormous amount of data freely available and at your fingertips.What is one thing we couldn't find out about you from an online search?I love Mexican folk music.I have been playing the guitar since I was 14 years old.The type of music I play is called corridos, and this is very popular in northern Mexico.I particularly enjoy playing and singing along; this is always a good party trick.Want to work with us?Check out our vacancies page or sign up for a job alert .At EMBL-EBI you can use your energy and skills to make a valuable contribution to science and technology and be part of a new generation: digital science.Behind its outstanding technical infrastructure and exceptional life science expertise, EMBL-EBI is a medium-sized organisation with a small-company feel.#J-*****-Ljbffr